© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22233
    Prev
    Next
    INDEX
    Explanations

    words related to vocalization and speech

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vocabulary and its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Redemption
    -0.73
     Cunningham
    -0.68
     Ceres
    -0.67
    uyomi
    -0.67
     Sisters
    -0.67
     Mara
    -0.66
     reconciliation
    -0.66
    Ô
    -0.65
     Dragonbound
    -0.64
    terson
    -0.64
    POSITIVE LOGITS
    ifer
    1.20
    abulary
    1.07
     voc
    1.06
    ationally
    0.99
    oded
    0.98
    ational
    0.98
    ally
    0.98
    ourses
    0.97
    oder
    0.96
    ations
    0.91
    Activations Density 0.012%

    No Known Activations